README.md

metadata

license: cc-by-nc-4.0
base_model: sfairXC/FsfairX-LLaMA3-RM-v0.1
tags:
  - easylm
  - alignment-handbook
  - trl
  - reward-trainer
  - generated_from_trainer
datasets:
  - helpsteer-rm
metrics:
  - accuracy
model-index:
  - name: easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: helpsteer-rm
          type: helpsteer-rm
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.664756446991404

easylm-helpsteer-rm-FsfairX-LLaMA3-RM-v0.1

This model is a fine-tuned version of sfairXC/FsfairX-LLaMA3-RM-v0.1 on the helpsteer-rm dataset. It achieves the following results on the evaluation set:

• Loss: 0.6508
• Accuracy: 0.6648

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 1

Training results

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1